Metadata-Version: 2.3
Name: dialz
Version: 1.1.3
Summary: 
Author: groovychoons
Author-email: siddiquezs2@cardiff.ac.uk
Requires-Python: >=3.10,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: accelerate (>=1.1.1,<2.0.0)
Requires-Dist: gguf (>=0.13.0,<0.14.0)
Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
Requires-Dist: scikit-learn (>=1.6.0,<2.0.0)
Requires-Dist: torch (>=2.5.1,<3.0.0)
Requires-Dist: transformers (>=4.46.3,<5.0.0)
Description-Content-Type: text/markdown

[![PyPI](https://img.shields.io/pypi/v/dialz?color=blue)](https://pypi.org/project/dialz/)
[![license](https://img.shields.io/badge/License-MIT-brightgreen.svg)](https://github.com/cardiffnlp/dialz/blob/master/LICENSE) 

# Dialz: A Python Toolkit for Steering Vectors

Docs: [https://cardiffnlp.github.io/dialz/](https://cardiffnlp.github.io/dialz/)

Paper: [https://www.arxiv.org/abs/2505.06262](https://www.arxiv.org/abs/2505.06262)

## About

Steering vectors allow users to modify activations at inference time to amplify or weaken a 'concept', e.g. honesty or positivity.

Dialz supports a diverse set of tasks, including creating contrastive pair datasets, computing and applying steering vectors, and visualizations.

A basic tutorial can be found [here](<notebooks/basic_tutorial.ipynb>).

## Installation

```
pip install dialz
```

Check out the [full documentation](https://cardiffnlp.github.io/dialz/) for usage information.

## Contributing

Any contributions to improve this project are welcome! Please open an issue or pull request in this repo with any changes you have.

## License

This code is released under a MIT license.

